Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Understand

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data.

• This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern.
• However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data.
• In this work, we show that these attacks presented in the literature are impractical in FL use-cases where the clients' training involves updating the Batch Normalization (BN) statistics and provide a new baseline attack that works for such scenarios.